Related papers: Quantization Backdoors to Deep Learning Commercial…

Model compression is vital to the deployment of deep learning on edge devices. Low precision representations, achieved via quantization of weights and activations, can reduce inference time and memory requirements. However, quantifying and…

Deep learning (DL) techniques are on the rise in the software engineering research community. More and more approaches have been developed on top of DL models, also due to the unprecedented amount of software-related data that can be used…

Recent advancements in on-device training for deep neural networks have underscored the critical need for efficient activation compression to overcome the memory constraints of mobile and edge devices. As activations dominate memory usage…

Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research. Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream…

Quantum deep learning (QDL) explores the use of both quantum and quantum-inspired resources to determine when deep learning's core capabilities, such as expressivity, generalization, and scalability, can be enhanced based on specific…

The growing computational demands of training large language models (LLMs) necessitate more efficient methods. Quantized training presents a promising solution by enabling low-bit arithmetic operations to reduce these costs. While FP8…

The rapid expansion of the Internet of Things (IoT) ecosystem has transformed various sectors but has also introduced significant cybersecurity challenges. Traditional centralized security methods often struggle to balance privacy…

As the applications of deep learning models on edge devices increase at an accelerating pace, fast adaptation to various scenarios with varying resource constraints has become a crucial aspect of model deployment. As a result, model…

Quantum machine learning (QML) promises significant computational advantages, yet models trained on sensitive data risk memorizing individual records, creating serious privacy vulnerabilities. While Quantum Differential Privacy (QDP)…

Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments. However, emerging studies on a few calibration dataset-free quantization methods suggest…

Local differential privacy (LDP) offers rigorous, quantifiable privacy guarantees for personal data by introducing perturbations at the data source. Understanding how these perturbations affect classifier utility is crucial for both…

Quantization is a practical technique for making large language models easier to deploy by reducing the precision used to store and operate on model weights. This can lower memory use and improve runtime feasibility on constrained hardware,…

How to efficiently serve ever-larger trained natural language models in practice has become exceptionally challenging even for powerful cloud servers due to their prohibitive memory/computation requirements. In this work, we present an…

Quantum neural networks (QNNs) are an important model for implementing quantum machine learning (QML), while they demonstrate a high degree of vulnerability to backdoor attacks similar to classical networks. To address this issue, a quantum…

A key challenge in Domain Generalization (DG) is preventing overfitting to source domains, which can be mitigated by finding flatter minima in the loss landscape. In this work, we propose Quantization-aware Training for Domain…

Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes…

Deploying Large Language Models (LLMs) on edge devices enhances privacy but faces performance hurdles due to limited resources. We introduce a systematic methodology to evaluate on-device LLMs, balancing capability, efficiency, and resource…

Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency. We systematically investigate the interplay between quantization precision (FP16, INT8, INT4) and…

Recently, there is a high demand for deploying DeepSeek-R1 and V3 locally, possibly because the official service often suffers from being busy and some organizations have data privacy concerns. While single-machine deployment offers…

Quantized deep neural networks (QDNNs) are necessary for low-power, high throughput, and embedded applications. Previous studies mostly focused on developing optimization methods for the quantization of given models. However, quantization…